cht42 commented on code in PR #19823: URL: https://github.com/apache/datafusion/pull/19823#discussion_r2693358605
########## datafusion/spark/src/function/datetime/date_part.rs: ########## @@ -0,0 +1,139 @@ +// Licensed to the Apache Software Foundation (ASF) under one +// or more contributor license agreements. See the NOTICE file +// distributed with this work for additional information +// regarding copyright ownership. The ASF licenses this file +// to you under the Apache License, Version 2.0 (the +// "License"); you may not use this file except in compliance +// with the License. You may obtain a copy of the License at +// +// http://www.apache.org/licenses/LICENSE-2.0 +// +// Unless required by applicable law or agreed to in writing, +// software distributed under the License is distributed on an +// "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY +// KIND, either express or implied. See the License for the +// specific language governing permissions and limitations +// under the License. + +use arrow::datatypes::{DataType, Field, FieldRef}; +use datafusion_common::types::logical_date; +use datafusion_common::{ + Result, ScalarValue, internal_err, types::logical_string, utils::take_function_args, +}; +use datafusion_expr::expr::ScalarFunction; +use datafusion_expr::simplify::{ExprSimplifyResult, SimplifyContext}; +use datafusion_expr::{ + Coercion, ColumnarValue, Expr, ReturnFieldArgs, ScalarFunctionArgs, ScalarUDFImpl, + Signature, TypeSignature, TypeSignatureClass, Volatility, +}; +use std::{any::Any, sync::Arc}; + +/// Wrapper around datafusion date_part function to handle +/// Spark behavior returning day of the week 1-indexed instead of 0-indexed and different part aliases. +/// <https://spark.apache.org/docs/latest/api/sql/index.html#date_part> +#[derive(Debug, PartialEq, Eq, Hash)] +pub struct SparkDatePart { + signature: Signature, + aliases: Vec<String>, +} + +impl Default for SparkDatePart { + fn default() -> Self { + Self::new() + } +} + +impl SparkDatePart { + pub fn new() -> Self { + Self { + signature: Signature::one_of( + vec![ + TypeSignature::Coercible(vec![ + Coercion::new_exact(TypeSignatureClass::Native(logical_string())), + Coercion::new_exact(TypeSignatureClass::Timestamp), + ]), + TypeSignature::Coercible(vec![ + Coercion::new_exact(TypeSignatureClass::Native(logical_string())), + Coercion::new_exact(TypeSignatureClass::Native(logical_date())), + ]), + ], + Volatility::Immutable, + ), + aliases: vec![String::from("datepart")], + } + } +} + +impl ScalarUDFImpl for SparkDatePart { + fn as_any(&self) -> &dyn Any { + self + } + + fn name(&self) -> &str { + "date_part" + } + + fn aliases(&self) -> &[String] { + &self.aliases + } + + fn signature(&self) -> &Signature { + &self.signature + } + + fn return_type(&self, _arg_types: &[DataType]) -> Result<DataType> { + internal_err!("Use return_field_from_args in this case instead.") + } + + fn return_field_from_args(&self, args: ReturnFieldArgs) -> Result<FieldRef> { + let nullable = args.arg_fields.iter().any(|f| f.is_nullable()); + + Ok(Arc::new(Field::new(self.name(), DataType::Int32, nullable))) + } + + fn invoke_with_args(&self, _args: ScalarFunctionArgs) -> Result<ColumnarValue> { + internal_err!("spark date_part should have been simplified to standard date_part") + } + + fn simplify( + &self, + args: Vec<Expr>, + _info: &SimplifyContext, + ) -> Result<ExprSimplifyResult> { + let [part_expr, date_expr] = take_function_args(self.name(), args)?; + + let part = match part_expr.as_literal() { + Some(ScalarValue::Utf8(Some(v))) | Some(ScalarValue::Utf8View(Some(v))) => { + v.to_lowercase() + } + _ => { + return internal_err!( + "First argument of `DATE_PART` must be non-null scalar Utf8" Review Comment: same as DF date_part, `part` is a literal https://github.com/apache/datafusion/blob/eadbed51b5c711423bc5f1a4d72fbf1e5be5d975/datafusion/functions/src/datetime/date_part.rs#L185 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
